Multimodal Integration for Heart Transplant Rejection


Chunqing (Tony) Liang

PhD student in Bioinformatics

Supervisor: Dr. Amrit Singh

Oct 6, 2025

Land acknowledgement

I would like to acknowledge that I work on the traditional, ancestral, and unceded territory of the Coast Salish Peoples, including the territories of the xwməθkwəy̓əm (Musqueam), Skwxwú7mesh (Squamish), Stó:lō and Səl̓ílwətaʔ/Selilwitulh (Tsleil- Waututh) Nations.

Traditional: Traditionally used and/or occupied by Musqueam people

Ancestral: Recognizes land that is handed down from generation to generation

Unceded: Refers to land that was not turned over to the Crown (government) by a treaty or other agreement

Background Heart Transplant

  • TODo

Background Heart Rejection

  • TODO

Background types of rejection …

Background ACR vs Quilty

  • TODO

Background Types of data

  • TODO

Background In-house data

  • In house cohort of \(> 500\) patients recorded from 2005 - 2025

  • Proof Centre

  • Bruce McManus Biobank

  • Cite collaborators

  • Or have their names and pic in here

Timeline of Data collection

  • Insert the timeline plot here

Collected data info

  • Add the table info of all available categories of data

Proof Centre

Bruce McManus Cardiovascular Biobank

Dr. Ying Wang Dr. Chi Lai

Objective

  • Improve diagnosis using multimodal data

  • Can we tell long term outcome of rejection?

Improve diagnosis using mulitmodal data

  • Add proposal fig of slide

Can we tell long term outcome of rejection

What method to apply

  • Need to know which method is most suitable to apply on this
  • Which there really isnt any after the pipeline run

MESSI pipeline

  • We created a workflow pipeline Multimodal Experiments with SyStematic Interrogation using nextflow
  • Built with Nextflow (1), Singularity (2)

MESSI pipeline

Standardized data preprocessing

  • Currently handles both R and Python –> could extend to more
  • Data flows in there , handles N different datasets
  • Important model selection prior to evaluation

Flexible method evaluation

  • Each method is an isolated workflow (dash box)
  • Each method internally runs evaluation in parallel
  • Each result is saved separately …
  • Easily extended to other tasks not just CV
  • On / Off to run interested methods only

Summarized reports of metrics performances

  • “Recursively” collects output from each method including versions
  • Summarizes metrics for downstream analysis
  • Provides rich report of computational resource usages

Computational Resources Usage

Performance on real-world datasets

Biological Interpretation on biomarkers identified

MESSI future direction

  • TODO

Current work on GeoMX

  • TODO

Background of GeoMX

  • TODO

GeoMx results 1

GeoMx results 2

GeoMx results 3

GeoMx results 4

  • TODO

Next steps

  • TODO

Conclusion

  • TODO

Discussion & Future directions

  • “No method works universally well on all datasets”
  • Classic statistical methods still work, and sometimes even better than deep learning (DL)
  • Pipeline proves way to reproducibly explore, benchmark different aspects of integration methods
    • Resumable
    • Parallel to compute as many resources as allowed at the same time
    • Ease burden of setting up environment
  • Need to add more methods and datasets
    • Especially DL models are more popular now
    • Explore if any dataset could have relation to another despite different disease/condition

Thanks!

Acknowledgements

  • Dr. Amrit Singh
  • Dr. Maryam Ahmadzadeh
  • Dr. Young Woong Kim
  • Rishika Daswani
  • Roy He
  • Samuel Leung
  • Raam Sivakumar
  • Jeffrey Tang
  • Michael Yoon
  • Mingming Zhang

Reference

1.
Di Tommaso P, Chatzou M, Floden EW, Barja PP, Palumbo E, Notredame C. Nextflow enables reproducible computational workflows. Nature biotechnology. 2017;35(4):316–9.
2.
Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PloS one. 2017;12(5):e0177459.